Quotas and Usage

GVR tracks request usage per API key through the user account's remainingRequests value.

Request cost by operation

The quota is deducted after processing succeeds. A successful unknown gender result also consumes quota.

Operation	Quota consumed
Standard Gender by Voice file request	1 request
Standard Gender by Voice URL request	1 request
Gender by Voice V2 (improved speech-aware analysis)	1 request
Gender by Voice V3 (advanced speaker-aware analysis)	2 requests
Voice age, deep voice fake, speech emotion, audio quality, speaker verification, image, or single-name request	1 request per successful API call
CSV validation	No requests; it checks whether the key has enough quota to process the rows.
CSV processing	1 request per CSV row processed.

CSV APIs

CSV processing is different because one file can contain many rows. The API checks the row count before processing and consumes one request per row.

If the file has more rows than the key has remaining requests, the API rejects the request before processing the CSV.

Response metadata

Many successful API responses include updated quota information:

{
  "remainingRequests": 2999
}

Use this value to show usage in your application or to trigger upgrade prompts before a user runs out of quota.

Quota errors

File and CSV endpoints can return a structured rate-limit response:

{
  "error": {
    "code": "RATE_LIMIT_EXCEEDED",
    "message": "You have exceeded your free tier limit of 50 requests.",
    "detailedMessage": "Insufficient remaining requests. Required: 1, Available: 0",
    "details": {
      "limit": 50,
      "used": 50,
      "reset_date": "2026-07-01T00:00:00.000Z"
    },
    "suggested_action": "Please upgrade to a premium plan to continue using the API."
  }
}

Single name endpoints can return:

{
  "error": "Insufficient remaining requests"
}

Practical guidance

• Validate required fields before calling the API.
• Avoid retry loops for validation errors.
• Treat remainingRequests as the source of truth after each API response.
• For CSV flows, validate the CSV before starting a large processing job.